联合Gabor滤波器和核池化特征学习的单样本人脸识别与验证  

Single Sample Face Recognition and Verification via Feature Learning with Gabor Filter and Kernel Pooling

作　　者：周稻祥 冯姝[3] ZHOU Daoxiang;FENG Shu(College of Data Science,Taiyuan University of Technology,Jinzhong 030600,China;School of Big Data and Software Engineering,Chongqing University,Chongqing 401331,China;Department of Foundation,Shanxi Agricultural University,Taigu 030801,China)

机构地区：[1]太原理工大学大数据学院,山西晋中030600 [2]重庆大学大数据与软件学院,重庆401331 [3]山西农业大学基础部,山西太谷030801

出　　处：《太原理工大学学报》2023年第2期384-391,共8页Journal of Taiyuan University of Technology

基　　金：国家自然科学基金资助项目(62101376);山西省应用基础研究计划基金项目(201901D211078,20210302124543)。

摘　　要：针对深度网络模型的结构复杂问题,受构建Gabor滤波器无需任何学习过程且与训练数据无关,以及径向基(radial basis function, RBF)核池化能够提取非线性二阶特征的启发,提出一种联合Gabor滤波器和RBF核池化的轻量卷积网络方法。首先对人脸图像进行Gabor卷积得到特征图;然后采用双曲正切函数tanh激励特征图以提高特征的表达能力;最后利用多尺度金字塔策略将特征图划分为多个区域,在每个区域上做RBF核池化,所有区域的核池化特征串联得到人脸特征表示。探讨了多个参数对识别性能的影响,对比了协方差池化和核池化的区别和性能。在三个单样本人脸识别和一个视频人脸验证数据集上进行大量实验,结果表明本文方法学习的人脸特征具有优秀的判别能力,对光照、遮挡、年龄等因素具有强鲁棒性。Aiming at the complex structure of deep network models, inspired by the fact that the construction of Gabor filters does not require any learning process and has nothing to do with training data, and that radial basis function(RBF) kernel pooling can extract nonlinear second-order features, a lightweight convolutional network approach combining Gabor filters and RBF kernel pooling was proposed. First, Gabor convolution is performed on the face image to obtain the feature map;then the hyperbolic tangent function tanh is used to activate the feature map with the hope of enhancing the discription ability of the feature;finally, the multi-scale pyramid strategy is applied to divide the feature map into multiple regions, RBF kernel pooling is conducted on each region, and the kernel pooling features of all regions are concatenated to obtain the face feature representation. The influence of multiple parameters on the recognition performance was discussed, and the difference and performance of covariance pooling and kernel pooling were compared. Extensive experiments were carried out on three single-sample face recognition datasets and one video face verification dataset. The results demonstrate that the face features learned by our method have excellent discriminative power and strong robustness to the factors such as illumination, occlusion, and age.

关 键 词：人脸识别 轻量卷积网络 GABOR滤波器 核池化 空间金字塔 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]